INDEX

Explanations

language relating to religious worship and judgment

oai_token-act-pair · gemini-2.0-flash

random snippets of text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ClientSize

-0.57

 kijk

-0.56

wpi

-0.56

Jegyzetek

-0.55

AddTagHelper

-0.55

 Diretto

-0.53

 Penh

-0.52

 intptr

-0.51

 Roskov

-0.50

paddingVertical

-0.49

POSITIVE LOGITS

verwijspagina

0.53

 labour

0.52

 mind

0.52

ंदीखरीदारी

0.51

 labor

0.51

hoeddwyd

0.50

ForRow

0.49

writeField

0.47

abestanden

0.47

rem

0.46

Activations Density 8.180%

language relating to religious worship and judgment

random snippets of text

No Known Activations